
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import warnings
import keras
from keras.layers import Dense
from keras.models import Sequential
import seaborn as sns
from keras import layers
import statsmodels.api as sm
import statsmodels.formula.api as smf
from sklearn.preprocessing import MinMaxScaler
import plotly.graph_objects as go
from tensorflow.keras import regularizers
import tensorflow as tf
from keras.preprocessing.sequence import TimeseriesGenerator
from io import StringIO
from keras.layers import LSTM, Dense
import chart_studio.tools as tls
from scipy import stats
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.preprocessing import MinMaxScaler
from sklearn.ensemble import RandomForestRegressor


pd.set_option('display.max_columns', None)
#loading Data
df = pd.read_excel (r'Project_static.xlsx')


df.head()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 738 entries, 0 to 737
Data columns (total 24 columns):
 #   Column                    Non-Null Count  Dtype         
---  ------                    --------------  -----         
 0   Date                      738 non-null    datetime64[ns]
 1   Gold_ETF                  738 non-null    float64       
 2   S&P_500                   738 non-null    float64       
 3   Silver                    738 non-null    float64       
 4   Platinum                  738 non-null    float64       
 5   Palladium                 738 non-null    float64       
 6   Crude_oil                 738 non-null    float64       
 7   Euro_USD_Exchange_Rate    738 non-null    float64       
 8   EGO                       738 non-null    float64       
 9   AU                        738 non-null    float64       
 10  ABX                       738 non-null    float64       
 11  BVN                       738 non-null    float64       
 12  CPI                       738 non-null    float64       
 13  Covid_deaths              738 non-null    int64         
 14  Interest_rate_USA         738 non-null    float64       
 15  Interest_rate_UK          738 non-null    float64       
 16  Disease_volitaly_tracker  738 non-null    float64       
 17  Gold_price_trend          738 non-null    int64         
 18  Covid_economic_impact     738 non-null    int64         
 19  Stock_maket_news          738 non-null    int64         
 20  Stock_market_crash        738 non-null    int64         
 21  silver_price_trend        738 non-null    int64         
 22  Palladium_price_trend     738 non-null    int64         
 23  Platinum_price_trend      738 non-null    int64         
dtypes: datetime64[ns](1), float64(15), int64(8)
memory usage: 138.5 KB


df.shape

(738, 24)


plt.rcParams["figure.figsize"] = (20,5)
df.plot(x='Date',y='Gold_ETF')

<AxesSubplot:xlabel='Date'>


plt.rcParams["figure.figsize"] = (20,5)
df.plot(x='Date',y='Silver')

<AxesSubplot:xlabel='Date'>


plt.rcParams["figure.figsize"] = (20,5)
df.plot(x='Date',y='Palladium')

<AxesSubplot:xlabel='Date'>


plt.rcParams["figure.figsize"] = (20,5)
df.plot(x='Date',y='Platinum')

<AxesSubplot:xlabel='Date'>


# For Time series reset index to Date


new_df = df.set_index('Date')
new_df.head()


plt.rcParams["figure.figsize"] = (20,10)
sns.heatmap(new_df.corr())

<AxesSubplot:>


new_df.corr()


def returns(col):
    return  col / col.shift(1) - 1


new_df['Gold_ETF_Return'] = returns(new_df['Gold_ETF'])
new_df['Silver_Return'] = returns(new_df['Silver'])
new_df['Platinum_Return'] = returns(new_df['Platinum'])
new_df['Palladium_Return'] = returns(new_df['Palladium'])


new_df.head()


new_df.isnull().sum()

Gold_ETF                    0
S&P_500                     0
Silver                      0
Platinum                    0
Palladium                   0
Crude_oil                   0
Euro_USD_Exchange_Rate      0
EGO                         0
AU                          0
ABX                         0
BVN                         0
CPI                         0
Covid_deaths                0
Interest_rate_USA           0
Interest_rate_UK            0
Disease_volitaly_tracker    0
Gold_price_trend            0
Covid_economic_impact       0
Stock_maket_news            0
Stock_market_crash          0
silver_price_trend          0
Palladium_price_trend       0
Platinum_price_trend        0
Gold_ETF_Return             1
Silver_Return               1
Platinum_Return             1
Palladium_Return            1
dtype: int64


new_df.dropna(inplace=True)


new_df.isnull().sum()

Gold_ETF                    0
S&P_500                     0
Silver                      0
Platinum                    0
Palladium                   0
Crude_oil                   0
Euro_USD_Exchange_Rate      0
EGO                         0
AU                          0
ABX                         0
BVN                         0
CPI                         0
Covid_deaths                0
Interest_rate_USA           0
Interest_rate_UK            0
Disease_volitaly_tracker    0
Gold_price_trend            0
Covid_economic_impact       0
Stock_maket_news            0
Stock_market_crash          0
silver_price_trend          0
Palladium_price_trend       0
Platinum_price_trend        0
Gold_ETF_Return             0
Silver_Return               0
Platinum_Return             0
Palladium_Return            0
dtype: int64


# Accuracy metrics
def forecast_accuracy(forecast, actual):
    me = np.mean(forecast - actual)             # ME
    mae = np.mean(np.abs(forecast - actual))    # MAE
    rmse = np.mean((forecast - actual)**2)**.5  # RMSE
    mse = np.mean((forecast - actual)**2)  # MSE

    return({ 'me':me, 'mae': mae, 
            'rmse':rmse,  
             'mse':mse})


new_df_gold = new_df.copy()
new_df_silver = new_df.copy()
new_df_platinum = new_df.copy()
new_df_palladium = new_df.copy()


test_size = int(0.3 * len(new_df_gold))
train_size = len(new_df_gold) - test_size

training_x = new_df_gold[:train_size].drop('Gold_ETF',axis=1)
training_y = new_df_gold[:train_size]['Gold_ETF']

testing_x = new_df_gold[train_size:].drop(['Gold_ETF'], axis=1)
testing_y = new_df_gold[train_size:]['Gold_ETF']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only
  x = pd.concat(x[::order], 1)

                            OLS Regression Results                            
==============================================================================
Dep. Variable:               Gold_ETF   R-squared:                       0.989
Model:                            OLS   Adj. R-squared:                  0.989
Method:                 Least Squares   F-statistic:                     1723.
Date:                Mon, 25 Jul 2022   Prob (F-statistic):               0.00
Time:                        21:14:43   Log-Likelihood:                -2207.7
No. Observations:                 516   AIC:                             4469.
Df Residuals:                     489   BIC:                             4584.
Df Model:                          26                                         
Covariance Type:            nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
const                      876.0314    264.485      3.312      0.001     356.364    1395.698
S&P_500                     -0.0277      0.011     -2.443      0.015      -0.050      -0.005
Silver                      16.8527      1.093     15.421      0.000      14.705      19.000
Platinum                    -0.1558      0.026     -5.903      0.000      -0.208      -0.104
Palladium                    0.0635      0.008      7.781      0.000       0.047       0.079
Crude_oil                   -0.3590      0.223     -1.611      0.108      -0.797       0.079
Euro_USD_Exchange_Rate     470.8142     70.163      6.710      0.000     332.955     608.673
EGO                          1.7104      1.113      1.537      0.125      -0.476       3.896
AU                           3.0267      0.714      4.238      0.000       1.624       4.430
ABX                          7.6814      0.825      9.311      0.000       6.060       9.302
BVN                         -6.2831      1.006     -6.247      0.000      -8.259      -4.307
CPI                         -0.6145      1.005     -0.611      0.541      -2.589       1.360
Covid_deaths                 0.0027      0.002      1.474      0.141      -0.001       0.006
Interest_rate_USA          -94.0916     11.722     -8.027      0.000    -117.123     -71.060
Interest_rate_UK            -6.2305     10.441     -0.597      0.551     -26.744      14.283
Disease_volitaly_tracker    -0.3056      0.134     -2.282      0.023      -0.569      -0.042
Gold_price_trend             0.6120      0.117      5.242      0.000       0.383       0.841
Covid_economic_impact       -0.1061      0.124     -0.853      0.394      -0.351       0.138
Stock_maket_news            -0.0494      0.057     -0.865      0.387      -0.162       0.063
Stock_market_crash          -0.1615      0.138     -1.170      0.242      -0.433       0.110
silver_price_trend          -0.3246      0.118     -2.750      0.006      -0.557      -0.093
Palladium_price_trend        0.1585      0.200      0.792      0.428      -0.234       0.551
Platinum_price_trend        -0.3373      0.168     -2.006      0.045      -0.668      -0.007
Gold_ETF_Return            458.4730    110.191      4.161      0.000     241.968     674.978
Silver_Return              -79.2051     57.883     -1.368      0.172    -192.935      34.525
Platinum_Return              6.3703     52.610      0.121      0.904     -96.999     109.740
Palladium_Return            -8.4088     35.944     -0.234      0.815     -79.033      62.215
==============================================================================
Omnibus:                        2.659   Durbin-Watson:                   0.321
Prob(Omnibus):                  0.265   Jarque-Bera (JB):                2.487
Skew:                           0.104   Prob(JB):                        0.288
Kurtosis:                       2.732   Cond. No.                     1.45e+06
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.45e+06. This might indicate that there are
strong multicollinearity or other numerical problems.


 # create regressor object
regressor = RandomForestRegressor(n_estimators = 500, random_state = 0)
 
# fit the regressor with x and y data
regressor.fit(training_x, training_y) 

pred = regressor.predict(testing_x)

importances = regressor.feature_importances_
importances

#Create a DataFrame using a Dictionary
data={'feature_names':training_x.columns,'feature_importance':importances}
fi_df = pd.DataFrame(data)
fi_df


#Sort the DataFrame in order decreasing feature importance
fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)

#Define size of bar plot
plt.figure(figsize=(10,8))
#Plot Searborn bar chart
sns.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'])
#Add chart labels
plt.title( 'FEATURE IMPORTANCE')
plt.xlabel('FEATURE IMPORTANCE')
plt.ylabel('FEATURE NAMES')

Text(0, 0.5, 'FEATURE NAMES')


col_to_remove = ['Silver_Return', 'Platinum_Return', 'Palladium_Return','Covid_economic_impact','Interest_rate_UK']


new_df_gold.drop(col_to_remove,axis=1,inplace=True)


scaler = MinMaxScaler()
feature_minmax_transform_data = scaler.fit_transform(new_df_gold)
feature_minmax_transform = pd.DataFrame(columns=new_df_gold.columns, data=feature_minmax_transform_data, index=new_df_gold.index)
feature_minmax_transform.head()


transformed_df = feature_minmax_transform


test_size = int(0.3 * len(transformed_df))
train_size = len(transformed_df) - test_size

training_x = transformed_df[:train_size].drop('Gold_ETF',axis=1)
training_y = transformed_df[:train_size]['Gold_ETF']

testing_x = transformed_df[train_size:].drop(['Gold_ETF'], axis=1)
testing_y = transformed_df[train_size:]['Gold_ETF']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:               Gold_ETF   R-squared:                       0.989
Model:                            OLS   Adj. R-squared:                  0.989
Method:                 Least Squares   F-statistic:                     2137.
Date:                Mon, 25 Jul 2022   Prob (F-statistic):               0.00
Time:                        21:14:46   Log-Likelihood:                 1136.0
No. Observations:                 516   AIC:                            -2228.
Df Residuals:                     494   BIC:                            -2135.
Df Model:                          21                                         
Covariance Type:            nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
const                        0.2180      0.032      6.885      0.000       0.156       0.280
S&P_500                     -0.0957      0.042     -2.277      0.023      -0.178      -0.013
Silver                       0.4487      0.028     15.772      0.000       0.393       0.505
Platinum                    -0.1599      0.027     -5.986      0.000      -0.212      -0.107
Palladium                    0.1468      0.019      7.843      0.000       0.110       0.184
Crude_oil                   -0.0783      0.053     -1.479      0.140      -0.182       0.026
Euro_USD_Exchange_Rate       0.1650      0.023      7.064      0.000       0.119       0.211
EGO                          0.0286      0.014      2.056      0.040       0.001       0.056
AU                           0.1056      0.025      4.294      0.000       0.057       0.154
ABX                          0.2126      0.022      9.618      0.000       0.169       0.256
BVN                         -0.1030      0.016     -6.338      0.000      -0.135      -0.071
CPI                         -0.0532      0.058     -0.912      0.362      -0.168       0.061
Covid_deaths                 0.0134      0.012      1.098      0.273      -0.011       0.037
Interest_rate_USA           -0.2887      0.025    -11.509      0.000      -0.338      -0.239
Disease_volitaly_tracker    -0.0391      0.013     -2.933      0.004      -0.065      -0.013
Gold_price_trend             0.0705      0.014      5.186      0.000       0.044       0.097
Stock_maket_news            -0.0037      0.008     -0.439      0.661      -0.020       0.013
Stock_market_crash          -0.0190      0.020     -0.973      0.331      -0.057       0.019
silver_price_trend          -0.0486      0.017     -2.931      0.004      -0.081      -0.016
Palladium_price_trend        0.0234      0.027      0.852      0.395      -0.031       0.077
Platinum_price_trend        -0.0348      0.015     -2.318      0.021      -0.064      -0.005
Gold_ETF_Return              0.0540      0.012      4.525      0.000       0.031       0.078
==============================================================================
Omnibus:                        3.755   Durbin-Watson:                   0.342
Prob(Omnibus):                  0.153   Jarque-Bera (JB):                3.243
Skew:                           0.109   Prob(JB):                        0.198
Kurtosis:                       2.679   Cond. No.                         121.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only
  x = pd.concat(x[::order], 1)


 # create regressor object
regressor = RandomForestRegressor(n_estimators = 500, random_state = 0)
 
# fit the regressor with x and y data
regressor.fit(training_x, training_y) 

pred = regressor.predict(testing_x)

importances = regressor.feature_importances_
importances

#Create a DataFrame using a Dictionary
data={'feature_names':training_x.columns,'feature_importance':importances}
fi_df = pd.DataFrame(data)
fi_df


#Sort the DataFrame in order decreasing feature importance
fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)

#Define size of bar plot
plt.figure(figsize=(10,8))
#Plot Searborn bar chart
sns.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'][:10])
#Add chart labels
plt.title( 'FEATURE IMPORTANCE')
plt.xlabel('FEATURE IMPORTANCE')
plt.ylabel('FEATURE NAMES')

Text(0, 0.5, 'FEATURE NAMES')


date_df = pd.DataFrame(transformed_df["Gold_ETF"])
date_df['Date'] = date_df.index
date_df.drop(columns="Gold_ETF",inplace=True)
date_df= date_df.squeeze()


float_data = np.array(transformed_df.values.tolist())


# Train-Test Split
nn_metal_data = float_data

split_percent = 0.70
split = int(split_percent*len(nn_metal_data))

nn_metal_train = nn_metal_data
nn_metal_test = nn_metal_data

date_train = date_df
date_test = date_df

print(len(nn_metal_train))
print(len(nn_metal_test))

737
737


look_back =3  #lags
numberOfCols = len(transformed_df.columns)
#train and test generator
train_generator = TimeseriesGenerator(nn_metal_train, nn_metal_train, length=look_back, batch_size=1)   
test_generator = TimeseriesGenerator(nn_metal_test, nn_metal_test, length=look_back, batch_size=1)


model = Sequential()
model.add(
    LSTM(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(64,
        activation='relu',
        activity_regularizer=regularizers.l2(0.01),
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.LSTM(80,
        activation='relu',
        input_shape=(look_back,numberOfCols))
)

model.add(Dense(numberOfCols))
model.compile(optimizer='adam', loss='mse')

num_epochs = 25
model.fit_generator(train_generator, epochs=num_epochs, verbose=1)

C:\Users\LOCAL_~1\Temp/ipykernel_10088/1287865284.py:31: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.
  model.fit_generator(train_generator, epochs=num_epochs, verbose=1)

Epoch 1/25
734/734 [==============================] - 8s 5ms/step - loss: 0.0381
Epoch 2/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0174
Epoch 3/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0122
Epoch 4/25
734/734 [==============================] - 5s 6ms/step - loss: 0.0107
Epoch 5/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0095
Epoch 6/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0091
Epoch 7/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0083A: 0s - los
Epoch 8/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0079
Epoch 9/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0076
Epoch 10/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0070
Epoch 11/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0068
Epoch 12/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0067
Epoch 13/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0064
Epoch 14/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0062
Epoch 15/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0060
Epoch 16/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0059
Epoch 17/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0058
Epoch 18/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0057
Epoch 19/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0057
Epoch 20/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0054
Epoch 21/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0056
Epoch 22/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0052
Epoch 23/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0053
Epoch 24/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0053
Epoch 25/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0052

<keras.callbacks.History at 0x21652908e80>


nn_metal_train = scaler.inverse_transform(nn_metal_train)
nn_metal_test = scaler.inverse_transform(nn_metal_test)


prediction = model.predict(test_generator)
nn_metal_train = nn_metal_train.reshape((-1))
nn_metal_train = nn_metal_train[::numberOfCols]
nn_metal_test = nn_metal_test.reshape((-1))
nn_metal_test = nn_metal_test[::numberOfCols]
prediction = scaler.inverse_transform(prediction)
prediction = prediction.reshape((-1))
prediction = prediction[::numberOfCols]

trace1 = go.Scatter(
    x = date_train,
    y = nn_metal_train,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = date_test,
    y = prediction,
    mode = 'lines',
    name = 'Predicted Value'
)
trace3 = go.Scatter(
    x = date_test,
    y = nn_metal_test,
    mode='lines',
    name = 'Actual values'
)
layout = go.Layout(
    title = "Price Predictions",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2, trace3], layout=layout)
fig.show()


forecast_accuracy(prediction, nn_metal_test[:734])

{'me': 5.428889020457253,
 'mae': 26.64802006609759,
 'rmse': 34.31694910105655,
 'mse': 1177.652995604506}


nn_metal_data = nn_metal_data.reshape((-1,numberOfCols))

def predict(num_prediction, model):
    
    prediction_list = nn_metal_data[-look_back:]
    for _ in range(num_prediction):
        prediction_list = prediction_list.reshape((-1,numberOfCols))
        #print(prediction_list)
        #prediction_list = scaler.inverse_transform(prediction_list)
        x = prediction_list[-look_back:]
        x = x.reshape((1,look_back, numberOfCols))
        out = model.predict(x)[0][0]
        for i in range(0,numberOfCols):
            prediction_list = np.append(prediction_list, model.predict(x)[0][i])
    prediction_list = scaler.inverse_transform(prediction_list.reshape((-1,numberOfCols)))
    prediction_list = prediction_list.reshape((-1))
    #prediction_list = prediction_list[look_back-1:]
    prediction_list = prediction_list[::numberOfCols]
    return prediction_list
    
def predict_dates(num_prediction):
    last_date = df['Date'].values[-2]
    prediction_dates = pd.date_range(last_date, periods=num_prediction+1, freq='D').tolist()
    return prediction_dates

num_prediction = 10
forecast = predict(num_prediction, model)
forecast_dates = predict_dates(num_prediction)
forecast = forecast[1:]


nn_metal_data = scaler.inverse_transform(nn_metal_data)
nn_metal_data = nn_metal_data.reshape((-1))
nn_metal_data = nn_metal_data[::numberOfCols]
forecast = forecast.reshape((-1))
#forecast_list1 = forecast[:5]
trace1 = go.Scatter(
    x = df['Date'],
    y = nn_metal_data,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = forecast_dates,
    y = forecast,
    mode = 'lines',
    name = 'forecast'
)

layout = go.Layout(
    title = "Forecasting Price",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2], layout=layout)
fig.show()


test_size = int(0.3 * len(new_df_silver))
train_size = len(new_df_silver) - test_size

training_x = new_df_silver[:train_size].drop('Silver',axis=1)
training_y = new_df_silver[:train_size]['Silver']

testing_x = new_df_silver[train_size:].drop(['Silver'], axis=1)
testing_y = new_df_silver[train_size:]['Silver']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:                 Silver   R-squared:                       0.984
Model:                            OLS   Adj. R-squared:                  0.983
Method:                 Least Squares   F-statistic:                     1124.
Date:                Mon, 25 Jul 2022   Prob (F-statistic):               0.00
Time:                        21:16:49   Log-Likelihood:                -462.05
No. Observations:                 516   AIC:                             978.1
Df Residuals:                     489   BIC:                             1093.
Df Model:                          26                                         
Covariance Type:            nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
const                      -91.0605      8.089    -11.257      0.000    -106.955     -75.167
Gold_ETF                     0.0194      0.001     15.421      0.000       0.017       0.022
S&P_500                   3.385e-05      0.000      0.087      0.930      -0.001       0.001
Platinum                     0.0137      0.001     19.966      0.000       0.012       0.015
Palladium                   -0.0019      0.000     -6.745      0.000      -0.002      -0.001
Crude_oil                    0.0073      0.008      0.965      0.335      -0.008       0.022
Euro_USD_Exchange_Rate      14.3797      2.402      5.986      0.000       9.660      19.100
EGO                         -0.0085      0.038     -0.223      0.823      -0.083       0.066
AU                          -0.1492      0.024     -6.287      0.000      -0.196      -0.103
ABX                          0.0560      0.030      1.851      0.065      -0.003       0.116
BVN                          0.3979      0.031     13.016      0.000       0.338       0.458
CPI                          0.1961      0.033      5.950      0.000       0.131       0.261
Covid_deaths                -0.0003   5.96e-05     -5.807      0.000      -0.000      -0.000
Interest_rate_USA            0.0493      0.423      0.117      0.907      -0.782       0.881
Interest_rate_UK            -0.9210      0.352     -2.616      0.009      -1.613      -0.229
Disease_volitaly_tracker     0.0035      0.005      0.768      0.443      -0.005       0.012
Gold_price_trend            -0.0031      0.004     -0.770      0.441      -0.011       0.005
Covid_economic_impact        0.0137      0.004      3.279      0.001       0.005       0.022
Stock_maket_news             0.0026      0.002      1.320      0.187      -0.001       0.006
Stock_market_crash          -0.0008      0.005     -0.170      0.865      -0.010       0.008
silver_price_trend           0.0256      0.004      6.616      0.000       0.018       0.033
Palladium_price_trend       -0.0100      0.007     -1.472      0.142      -0.023       0.003
Platinum_price_trend        -0.0151      0.006     -2.658      0.008      -0.026      -0.004
Gold_ETF_Return            -13.7449      3.755     -3.661      0.000     -21.122      -6.368
Silver_Return                6.8719      1.944      3.535      0.000       3.053      10.691
Platinum_Return             -4.5686      1.774     -2.576      0.010      -8.054      -1.084
Palladium_Return             2.0314      1.217      1.670      0.096      -0.359       4.422
==============================================================================
Omnibus:                        1.816   Durbin-Watson:                   0.289
Prob(Omnibus):                  0.403   Jarque-Bera (JB):                1.707
Skew:                           0.048   Prob(JB):                        0.426
Kurtosis:                       3.265   Cond. No.                     1.40e+06
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.4e+06. This might indicate that there are
strong multicollinearity or other numerical problems.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning:

In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only


 # create regressor object
regressor = RandomForestRegressor(n_estimators = 500, random_state = 0)
 
# fit the regressor with x and y data
regressor.fit(training_x, training_y) 

pred = regressor.predict(testing_x)

importances = regressor.feature_importances_
importances

#Create a DataFrame using a Dictionary
data={'feature_names':training_x.columns,'feature_importance':importances}
fi_df = pd.DataFrame(data)
fi_df


#Sort the DataFrame in order decreasing feature importance
fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)

#Define size of bar plot
plt.figure(figsize=(10,8))
#Plot Searborn bar chart
sns.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'][:10])
#Add chart labels
plt.title( 'FEATURE IMPORTANCE')
plt.xlabel('FEATURE IMPORTANCE')
plt.ylabel('FEATURE NAMES')

Text(0, 0.5, 'FEATURE NAMES')


col_to_remove = ['EGO','Interest_rate_USA','Palladium_price_trend','Gold_price_trend']


new_df_silver.drop(col_to_remove,axis=1,inplace=True)


scaler = MinMaxScaler()
feature_minmax_transform_data = scaler.fit_transform(new_df_silver)
feature_minmax_transform = pd.DataFrame(columns=new_df_silver.columns, data=feature_minmax_transform_data, index=new_df_silver.index)
feature_minmax_transform.head()
transformed_df = feature_minmax_transform


test_size = int(0.3 * len(transformed_df))
train_size = len(transformed_df) - test_size

training_x = transformed_df[:train_size].drop('Silver',axis=1)
training_y = transformed_df[:train_size]['Silver']

testing_x = transformed_df[train_size:].drop(['Silver'], axis=1)
testing_y = transformed_df[train_size:]['Silver']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:                 Silver   R-squared:                       0.983
Model:                            OLS   Adj. R-squared:                  0.983
Method:                 Least Squares   F-statistic:                     1329.
Date:                Mon, 25 Jul 2022   Prob (F-statistic):               0.00
Time:                        21:16:52   Log-Likelihood:                 1017.8
No. Observations:                 516   AIC:                            -1990.
Df Residuals:                     493   BIC:                            -1892.
Df Model:                          22                                         
Covariance Type:            nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
const                       -0.2636      0.037     -7.068      0.000      -0.337      -0.190
Gold_ETF                     0.7018      0.041     17.275      0.000       0.622       0.782
S&P_500                      0.0171      0.055      0.312      0.755      -0.090       0.124
Platinum                     0.5492      0.025     22.133      0.000       0.500       0.598
Palladium                   -0.1934      0.021     -9.421      0.000      -0.234      -0.153
Crude_oil                    0.0509      0.068      0.753      0.452      -0.082       0.184
Euro_USD_Exchange_Rate       0.1972      0.030      6.537      0.000       0.138       0.257
AU                          -0.2015      0.030     -6.778      0.000      -0.260      -0.143
ABX                          0.0701      0.030      2.302      0.022       0.010       0.130
BVN                          0.2588      0.018     14.537      0.000       0.224       0.294
CPI                          0.4657      0.069      6.731      0.000       0.330       0.602
Covid_deaths                -0.0906      0.014     -6.375      0.000      -0.118      -0.063
Interest_rate_UK            -0.1563      0.041     -3.808      0.000      -0.237      -0.076
Disease_volitaly_tracker     0.0142      0.017      0.819      0.413      -0.020       0.048
Covid_economic_impact        0.0783      0.023      3.372      0.001       0.033       0.124
Stock_maket_news             0.0158      0.011      1.445      0.149      -0.006       0.037
Stock_market_crash          -0.0291      0.021     -1.387      0.166      -0.070       0.012
silver_price_trend           0.1218      0.019      6.483      0.000       0.085       0.159
Platinum_price_trend        -0.0685      0.017     -3.977      0.000      -0.102      -0.035
Gold_ETF_Return             -0.0873      0.023     -3.775      0.000      -0.133      -0.042
Silver_Return                0.1100      0.030      3.646      0.000       0.051       0.169
Platinum_Return             -0.0616      0.023     -2.636      0.009      -0.107      -0.016
Palladium_Return             0.0581      0.032      1.836      0.067      -0.004       0.120
==============================================================================
Omnibus:                        2.146   Durbin-Watson:                   0.288
Prob(Omnibus):                  0.342   Jarque-Bera (JB):                2.003
Skew:                           0.087   Prob(JB):                        0.367
Kurtosis:                       3.251   Cond. No.                         120.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning:

In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only


len(new_df.columns)

27


date_df = pd.DataFrame(transformed_df["Silver"])
date_df['Date'] = date_df.index
date_df.drop(columns="Silver",inplace=True)
date_df= date_df.squeeze()


float_data = np.array(transformed_df.values.tolist())


# Train-Test Split
nn_metal_data = float_data

split_percent = 0.70
split = int(split_percent*len(nn_metal_data))

nn_metal_train = nn_metal_data
nn_metal_test = nn_metal_data

date_train = date_df
date_test = date_df

print(len(nn_metal_train))
print(len(nn_metal_test))

737
737


look_back =3  #lags
numberOfCols = len(transformed_df.columns)
#train and test generator
train_generator = TimeseriesGenerator(nn_metal_train, nn_metal_train, length=look_back, batch_size=1)   
test_generator = TimeseriesGenerator(nn_metal_test, nn_metal_test, length=look_back, batch_size=1)


model = Sequential()
model.add(
    LSTM(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(64,
        activation='relu',
        activity_regularizer=regularizers.l2(0.01),
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.LSTM(80,
        activation='relu',
        input_shape=(look_back,numberOfCols))
)

model.add(Dense(numberOfCols))
model.compile(optimizer='adam', loss='mse')

num_epochs = 25
model.fit_generator(train_generator, epochs=num_epochs, verbose=1)

C:\Users\LOCAL_~1\Temp/ipykernel_10088/1287865284.py:31: UserWarning:

`Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.

Epoch 1/25
734/734 [==============================] - 8s 5ms/step - loss: 0.0336
Epoch 2/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0151
Epoch 3/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0128
Epoch 4/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0110
Epoch 5/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0096
Epoch 6/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0086
Epoch 7/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0081
Epoch 8/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0076
Epoch 9/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0074
Epoch 10/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0073
Epoch 11/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0068
Epoch 12/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0067
Epoch 13/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0065
Epoch 14/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0065
Epoch 15/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0062
Epoch 16/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0064
Epoch 17/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0061
Epoch 18/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0057
Epoch 19/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0058
Epoch 20/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0057
Epoch 21/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0056
Epoch 22/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0056
Epoch 23/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0054
Epoch 24/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0054
Epoch 25/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0053

<keras.callbacks.History at 0x2165ec5f700>


nn_metal_train = scaler.inverse_transform(nn_metal_train)
nn_metal_test = scaler.inverse_transform(nn_metal_test)


prediction = model.predict(test_generator)
nn_metal_train = nn_metal_train.reshape((-1))
nn_metal_train = nn_metal_train[2::numberOfCols]
nn_metal_test = nn_metal_test.reshape((-1))
nn_metal_test = nn_metal_test[2::numberOfCols]
prediction = scaler.inverse_transform(prediction)
prediction = prediction.reshape((-1))
prediction = prediction[2::numberOfCols]

trace1 = go.Scatter(
    x = date_train,
    y = nn_metal_train,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = date_test,
    y = prediction,
    mode = 'lines',
    name = 'Predicted Value'
)
trace3 = go.Scatter(
    x = date_test,
    y = nn_metal_test,
    mode='lines',
    name = 'Actual values'
)
layout = go.Layout(
    title = "Price Predictions",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2, trace3], layout=layout)
fig.show()


forecast_accuracy(prediction, nn_metal_test[:734])

{'me': -0.27585079067344564,
 'mae': 0.6882383668052403,
 'rmse': 0.9010776606976739,
 'mse': 0.8119409506083924}


nn_metal_data = nn_metal_data.reshape((-1,numberOfCols))

def predict(num_prediction, model):
    
    prediction_list = nn_metal_data[-look_back:]
    for _ in range(num_prediction):
        prediction_list = prediction_list.reshape((-1,numberOfCols))
        #print(prediction_list)
        #prediction_list = scaler.inverse_transform(prediction_list)
        x = prediction_list[-look_back:]
        x = x.reshape((1,look_back, numberOfCols))
        out = model.predict(x)[0][0]
        for i in range(0,numberOfCols):
            prediction_list = np.append(prediction_list, model.predict(x)[0][i])
    prediction_list = scaler.inverse_transform(prediction_list.reshape((-1,numberOfCols)))
    prediction_list = prediction_list.reshape((-1))
    #prediction_list = prediction_list[look_back-1:]
    prediction_list = prediction_list[2::numberOfCols]
    return prediction_list
    
def predict_dates(num_prediction):
    last_date = df['Date'].values[-2]
    prediction_dates = pd.date_range(last_date, periods=num_prediction+1, freq='D').tolist()
    return prediction_dates

num_prediction = 10
forecast = predict(num_prediction, model)
forecast_dates = predict_dates(num_prediction)
forecast = forecast[1:]


nn_metal_data = scaler.inverse_transform(nn_metal_data)
nn_metal_data = nn_metal_data.reshape((-1))
nn_metal_data = nn_metal_data[2::numberOfCols]
forecast = forecast.reshape((-1))
#forecast_list1 = forecast[:5]
trace1 = go.Scatter(
    x = df['Date'],
    y = nn_metal_data,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = forecast_dates,
    y = forecast,
    mode = 'lines',
    name = 'forecast'
)

layout = go.Layout(
    title = "Forecasting Price",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2], layout=layout)
fig.show()


test_size = int(0.3 * len(new_df_platinum))
train_size = len(new_df_platinum) - test_size

training_x = new_df_platinum[:train_size].drop('Platinum',axis=1)
training_y = new_df_platinum[:train_size]['Platinum']

testing_x = new_df_platinum[train_size:].drop(['Platinum'], axis=1)
testing_y = new_df_platinum[train_size:]['Platinum']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:               Platinum   R-squared:                       0.957
Model:                            OLS   Adj. R-squared:                  0.955
Method:                 Least Squares   F-statistic:                     419.4
Date:                Mon, 25 Jul 2022   Prob (F-statistic):          3.81e-315
Time:                        21:18:46   Log-Likelihood:                -2467.7
No. Observations:                 516   AIC:                             4989.
Df Residuals:                     489   BIC:                             5104.
Df Model:                          26                                         
Covariance Type:            nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
const                     3930.7932    405.307      9.698      0.000    3134.435    4727.151
Gold_ETF                    -0.4268      0.072     -5.903      0.000      -0.569      -0.285
S&P_500                      0.0744      0.019      4.001      0.000       0.038       0.111
Silver                      32.6746      1.637     19.966      0.000      29.459      35.890
Palladium                    0.1447      0.013     11.374      0.000       0.120       0.170
Crude_oil                    0.4437      0.369      1.202      0.230      -0.282       1.169
Euro_USD_Exchange_Rate    -563.7905    118.631     -4.752      0.000    -796.881    -330.700
EGO                          3.9646      1.837      2.158      0.031       0.355       7.574
AU                          11.3305      1.089     10.407      0.000       9.191      13.470
ABX                         -9.4887      1.418     -6.692      0.000     -12.275      -6.703
BVN                        -16.0734      1.569    -10.242      0.000     -19.157     -12.990
CPI                        -10.8402      1.590     -6.818      0.000     -13.964      -7.716
Covid_deaths                 0.0232      0.003      8.253      0.000       0.018       0.029
Interest_rate_USA           99.3033     20.142      4.930      0.000      59.728     138.879
Interest_rate_UK            39.1819     17.193      2.279      0.023       5.401      72.963
Disease_volitaly_tracker    -0.0269      0.223     -0.121      0.904      -0.465       0.411
Gold_price_trend            -0.4207      0.198     -2.129      0.034      -0.809      -0.032
Covid_economic_impact       -0.9563      0.201     -4.747      0.000      -1.352      -0.561
Stock_maket_news            -0.3250      0.093     -3.478      0.001      -0.509      -0.141
Stock_market_crash           0.5200      0.227      2.286      0.023       0.073       0.967
silver_price_trend          -0.6082      0.195     -3.120      0.002      -0.991      -0.225
Palladium_price_trend        0.1655      0.331      0.500      0.617      -0.485       0.816
Platinum_price_trend         2.1194      0.262      8.075      0.000       1.604       2.635
Gold_ETF_Return            321.6001    184.981      1.739      0.083     -41.856     685.056
Silver_Return             -211.3560     95.496     -2.213      0.027    -398.989     -23.723
Platinum_Return            379.9889     85.352      4.452      0.000     212.287     547.691
Palladium_Return          -184.0042     58.902     -3.124      0.002    -299.736     -68.273
==============================================================================
Omnibus:                        0.938   Durbin-Watson:                   0.416
Prob(Omnibus):                  0.626   Jarque-Bera (JB):                0.996
Skew:                           0.035   Prob(JB):                        0.608
Kurtosis:                       2.796   Cond. No.                     1.41e+06
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.41e+06. This might indicate that there are
strong multicollinearity or other numerical problems.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning:

In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only


 # create regressor object
regressor = RandomForestRegressor(n_estimators = 500, random_state = 0)
 
# fit the regressor with x and y data
regressor.fit(training_x, training_y) 

pred = regressor.predict(testing_x)

importances = regressor.feature_importances_
importances

#Create a DataFrame using a Dictionary
data={'feature_names':training_x.columns,'feature_importance':importances}
fi_df = pd.DataFrame(data)
fi_df


#Sort the DataFrame in order decreasing feature importance
fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)

#Define size of bar plot
plt.figure(figsize=(10,8))
#Plot Searborn bar chart
sns.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'][:10])
#Add chart labels
plt.title( 'FEATURE IMPORTANCE')
plt.xlabel('FEATURE IMPORTANCE')
plt.ylabel('FEATURE NAMES')

Text(0, 0.5, 'FEATURE NAMES')


new_df.columns

Index(['Gold_ETF', 'S&P_500', 'Silver', 'Platinum', 'Palladium', 'Crude_oil',
       'Euro_USD_Exchange_Rate', 'EGO', 'AU', 'ABX', 'BVN', 'CPI',
       'Covid_deaths', 'Interest_rate_USA', 'Interest_rate_UK',
       'Disease_volitaly_tracker', 'Gold_price_trend', 'Covid_economic_impact',
       'Stock_maket_news', 'Stock_market_crash', 'silver_price_trend',
       'Palladium_price_trend', 'Platinum_price_trend', 'Gold_ETF_Return',
       'Silver_Return', 'Platinum_Return', 'Palladium_Return'],
      dtype='object')


col_to_remove = ['Palladium_price_trend','Disease_volitaly_tracker']


new_df_platinum.drop(col_to_remove,axis=1,inplace=True)


scaler = MinMaxScaler()
feature_minmax_transform_data = scaler.fit_transform(new_df_platinum)
feature_minmax_transform = pd.DataFrame(columns=new_df_platinum.columns, data=feature_minmax_transform_data, index=new_df_platinum.index)
feature_minmax_transform.head()
transformed_df = feature_minmax_transform


test_size = int(0.3 * len(transformed_df))
train_size = len(transformed_df) - test_size

training_x = transformed_df[:train_size].drop('Platinum',axis=1)
training_y = transformed_df[:train_size]['Platinum']

testing_x = transformed_df[train_size:].drop(['Platinum'], axis=1)
testing_y = transformed_df[train_size:]['Platinum']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:               Platinum   R-squared:                       0.957
Model:                            OLS   Adj. R-squared:                  0.955
Method:                 Least Squares   F-statistic:                     455.9
Date:                Mon, 25 Jul 2022   Prob (F-statistic):          9.59e-318
Time:                        21:18:50   Log-Likelihood:                 908.62
No. Observations:                 516   AIC:                            -1767.
Df Residuals:                     491   BIC:                            -1661.
Df Model:                          24                                         
Covariance Type:            nonrobust                                         
==========================================================================================
                             coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------------------
const                      0.0437      0.056      0.785      0.433      -0.066       0.153
Gold_ETF                  -0.4001      0.068     -5.918      0.000      -0.533      -0.267
S&P_500                    0.2754      0.068      4.049      0.000       0.142       0.409
Silver                     0.8290      0.041     20.029      0.000       0.748       0.910
Palladium                  0.3390      0.023     14.477      0.000       0.293       0.385
Crude_oil                  0.1121      0.083      1.343      0.180      -0.052       0.276
Euro_USD_Exchange_Rate    -0.1901      0.038     -5.049      0.000      -0.264      -0.116
EGO                        0.0509      0.024      2.114      0.035       0.004       0.098
AU                         0.3765      0.036     10.442      0.000       0.306       0.447
ABX                       -0.2580      0.038     -6.720      0.000      -0.333      -0.183
BVN                       -0.2676      0.026    -10.469      0.000      -0.318      -0.217
CPI                       -0.6378      0.086     -7.375      0.000      -0.808      -0.468
Covid_deaths               0.1564      0.019      8.443      0.000       0.120       0.193
Interest_rate_USA          0.2633      0.052      5.024      0.000       0.160       0.366
Interest_rate_UK           0.1599      0.068      2.359      0.019       0.027       0.293
Gold_price_trend          -0.0441      0.021     -2.078      0.038      -0.086      -0.002
Covid_economic_impact     -0.1392      0.029     -4.877      0.000      -0.195      -0.083
Stock_maket_news          -0.0468      0.013     -3.489      0.001      -0.073      -0.020
Stock_market_crash         0.0763      0.028      2.693      0.007       0.021       0.132
silver_price_trend        -0.0791      0.026     -3.082      0.002      -0.130      -0.029
Platinum_price_trend       0.1887      0.022      8.476      0.000       0.145       0.232
Gold_ETF_Return            0.0516      0.029      1.782      0.075      -0.005       0.109
Silver_Return             -0.0847      0.038     -2.253      0.025      -0.159      -0.011
Platinum_Return            0.1278      0.029      4.450      0.000       0.071       0.184
Palladium_Return          -0.1241      0.039     -3.204      0.001      -0.200      -0.048
==============================================================================
Omnibus:                        0.988   Durbin-Watson:                   0.417
Prob(Omnibus):                  0.610   Jarque-Bera (JB):                1.030
Skew:                           0.027   Prob(JB):                        0.598
Kurtosis:                       2.788   Cond. No.                         124.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning:

In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only


date_df = pd.DataFrame(transformed_df["Platinum"])
date_df['Date'] = date_df.index
date_df.drop(columns="Platinum",inplace=True)
date_df= date_df.squeeze()


float_data = np.array(transformed_df.values.tolist())


# Train-Test Split
nn_metal_data = float_data

split_percent = 0.70
split = int(split_percent*len(nn_metal_data))

nn_metal_train = nn_metal_data
nn_metal_test = nn_metal_data

date_train = date_df
date_test = date_df

print(len(nn_metal_train))
print(len(nn_metal_test))

737
737


look_back =3  #lags
numberOfCols = len(transformed_df.columns)
#train and test generator
train_generator = TimeseriesGenerator(nn_metal_train, nn_metal_train, length=look_back, batch_size=1)   
test_generator = TimeseriesGenerator(nn_metal_test, nn_metal_test, length=look_back, batch_size=1)


model = Sequential()
model.add(
    LSTM(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(64,
        activation='relu',
        activity_regularizer=regularizers.l2(0.01),
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.LSTM(80,
        activation='relu',
        input_shape=(look_back,numberOfCols))
)

model.add(Dense(numberOfCols))
model.compile(optimizer='adam', loss='mse')

num_epochs = 25
model.fit_generator(train_generator, epochs=num_epochs, verbose=1)

C:\Users\LOCAL_~1\Temp/ipykernel_10088/1287865284.py:31: UserWarning:

`Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.

Epoch 1/25
734/734 [==============================] - 8s 5ms/step - loss: 0.0340
Epoch 2/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0136
Epoch 3/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0104
Epoch 4/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0095
Epoch 5/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0085
Epoch 6/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0080
Epoch 7/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0074
Epoch 8/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0072
Epoch 9/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0069
Epoch 10/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0065
Epoch 11/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0064
Epoch 12/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0064
Epoch 13/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0060
Epoch 14/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0059
Epoch 15/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0060
Epoch 16/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0056
Epoch 17/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0055
Epoch 18/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0056
Epoch 19/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0054
Epoch 20/25
734/734 [==============================] - 5s 7ms/step - loss: 0.0053A: 0s 
Epoch 21/25
734/734 [==============================] - 5s 7ms/step - loss: 0.0054
Epoch 22/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0051
Epoch 23/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0050
Epoch 24/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0049
Epoch 25/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0048

<keras.callbacks.History at 0x21666aeda60>


nn_metal_train = scaler.inverse_transform(nn_metal_train)
nn_metal_test = scaler.inverse_transform(nn_metal_test)


prediction = model.predict(test_generator)
nn_metal_train = nn_metal_train.reshape((-1))
nn_metal_train = nn_metal_train[3::numberOfCols]
nn_metal_test = nn_metal_test.reshape((-1))
nn_metal_test = nn_metal_test[3::numberOfCols]
prediction = scaler.inverse_transform(prediction)
prediction = prediction.reshape((-1))
prediction = prediction[3::numberOfCols]

trace1 = go.Scatter(
    x = date_train,
    y = nn_metal_train,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = date_test,
    y = prediction,
    mode = 'lines',
    name = 'Predicted Value'
)
trace3 = go.Scatter(
    x = date_test,
    y = nn_metal_test,
    mode='lines',
    name = 'Actual values'
)
layout = go.Layout(
    title = "Price Predictions",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2, trace3], layout=layout)
fig.show()


forecast_accuracy(prediction, nn_metal_test[:734])

{'me': 3.995765873132025,
 'mae': 29.144590073255497,
 'rmse': 37.77006171478542,
 'mse': 1426.5775619386995}


nn_metal_data = nn_metal_data.reshape((-1,numberOfCols))

def predict(num_prediction, model):
    
    prediction_list = nn_metal_data[-look_back:]
    for _ in range(num_prediction):
        prediction_list = prediction_list.reshape((-1,numberOfCols))
        #print(prediction_list)
        #prediction_list = scaler.inverse_transform(prediction_list)
        x = prediction_list[-look_back:]
        x = x.reshape((1,look_back, numberOfCols))
        out = model.predict(x)[0][0]
        for i in range(0,numberOfCols):
            prediction_list = np.append(prediction_list, model.predict(x)[0][i])
    prediction_list = scaler.inverse_transform(prediction_list.reshape((-1,numberOfCols)))
    prediction_list = prediction_list.reshape((-1))
    #prediction_list = prediction_list[look_back-1:]
    prediction_list = prediction_list[3::numberOfCols]
    return prediction_list
    
def predict_dates(num_prediction):
    last_date = df['Date'].values[-2]
    prediction_dates = pd.date_range(last_date, periods=num_prediction+1, freq='D').tolist()
    return prediction_dates

num_prediction = 10
forecast = predict(num_prediction, model)
forecast_dates = predict_dates(num_prediction)
forecast = forecast[1:]


nn_metal_data = scaler.inverse_transform(nn_metal_data)
nn_metal_data = nn_metal_data.reshape((-1))
nn_metal_data = nn_metal_data[3::numberOfCols]
forecast = forecast.reshape((-1))
#forecast_list1 = forecast[:5]
trace1 = go.Scatter(
    x = df['Date'],
    y = nn_metal_data,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = forecast_dates,
    y = forecast,
    mode = 'lines',
    name = 'forecast'
)

layout = go.Layout(
    title = "Forecasting Price",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2], layout=layout)
fig.show()


test_size = int(0.3 * len(new_df_palladium))
train_size = len(new_df_palladium) - test_size

training_x = new_df_palladium[:train_size].drop('Palladium',axis=1)
training_y = new_df_palladium[:train_size]['Palladium']

testing_x = new_df_palladium[train_size:].drop(['Palladium'], axis=1)
testing_y = new_df_palladium[train_size:]['Palladium']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:              Palladium   R-squared:                       0.949
Model:                            OLS   Adj. R-squared:                  0.947
Method:                 Least Squares   F-statistic:                     351.9
Date:                Mon, 25 Jul 2022   Prob (F-statistic):          1.91e-297
Time:                        21:20:46   Log-Likelihood:                -3061.4
No. Observations:                 516   AIC:                             6177.
Df Residuals:                     489   BIC:                             6291.
Df Model:                          26                                         
Covariance Type:            nonrobust                                         
============================================================================================
                               coef    std err          t      P>|t|      [0.025      0.975]
--------------------------------------------------------------------------------------------
const                    -8633.3808   1342.971     -6.429      0.000   -1.13e+04   -5994.675
Gold_ETF                     1.7358      0.223      7.781      0.000       1.298       2.174
S&P_500                      0.3205      0.058      5.533      0.000       0.207       0.434
Silver                     -44.9547      6.664     -6.745      0.000     -58.049     -31.860
Platinum                     1.4454      0.127     11.374      0.000       1.196       1.695
Crude_oil                   -5.9490      1.137     -5.231      0.000      -8.183      -3.715
Euro_USD_Exchange_Rate    -545.0489    382.652     -1.424      0.155   -1296.895     206.797
EGO                         10.2883      5.814      1.770      0.077      -1.135      21.712
AU                         -15.7094      3.735     -4.206      0.000     -23.049      -8.370
ABX                         -4.8992      4.676     -1.048      0.295     -14.087       4.288
BVN                         28.4972      5.311      5.365      0.000      18.062      38.933
CPI                         28.6183      5.096      5.616      0.000      18.606      38.631
Covid_deaths                -0.0403      0.009     -4.322      0.000      -0.059      -0.022
Interest_rate_USA         -156.5867     64.828     -2.415      0.016    -283.962     -29.212
Interest_rate_UK            49.3423     54.574      0.904      0.366     -57.886     156.570
Disease_volitaly_tracker     0.7730      0.703      1.099      0.272      -0.609       2.155
Gold_price_trend            -1.1202      0.625     -1.791      0.074      -2.349       0.109
Covid_economic_impact        2.2294      0.643      3.466      0.001       0.966       3.493
Stock_maket_news             2.1449      0.283      7.586      0.000       1.589       2.700
Stock_market_crash          -1.5259      0.719     -2.121      0.034      -2.939      -0.112
silver_price_trend          -1.9556      0.616     -3.176      0.002      -3.166      -0.746
Palladium_price_trend       11.8981      0.898     13.255      0.000      10.134      13.662
Platinum_price_trend        -6.6230      0.831     -7.973      0.000      -8.255      -4.991
Gold_ETF_Return          -1255.5072    583.604     -2.151      0.032   -2402.189    -108.826
Silver_Return              378.9152    302.798      1.251      0.211    -216.030     973.861
Platinum_Return           -611.9661    273.736     -2.236      0.026   -1149.811     -74.121
Palladium_Return          1015.8034    182.284      5.573      0.000     657.648    1373.959
==============================================================================
Omnibus:                        9.482   Durbin-Watson:                   0.452
Prob(Omnibus):                  0.009   Jarque-Bera (JB):                9.479
Skew:                           0.307   Prob(JB):                      0.00874
Kurtosis:                       3.253   Cond. No.                     1.34e+06
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.34e+06. This might indicate that there are
strong multicollinearity or other numerical problems.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning:

In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only


 # create regressor object
regressor = RandomForestRegressor(n_estimators = 500, random_state = 0)
 
# fit the regressor with x and y data
regressor.fit(training_x, training_y) 

pred = regressor.predict(testing_x)

importances = regressor.feature_importances_
importances

#Create a DataFrame using a Dictionary
data={'feature_names':training_x.columns,'feature_importance':importances}
fi_df = pd.DataFrame(data)
fi_df


#Sort the DataFrame in order decreasing feature importance
fi_df.sort_values(by=['feature_importance'], ascending=False,inplace=True)

#Define size of bar plot
plt.figure(figsize=(10,8))
#Plot Searborn bar chart
sns.barplot(x=fi_df['feature_importance'], y=fi_df['feature_names'][:10])
#Add chart labels
plt.title( 'FEATURE IMPORTANCE')
plt.xlabel('FEATURE IMPORTANCE')
plt.ylabel('FEATURE NAMES')

Text(0, 0.5, 'FEATURE NAMES')


new_df.columns

Index(['Gold_ETF', 'S&P_500', 'Silver', 'Platinum', 'Palladium', 'Crude_oil',
       'Euro_USD_Exchange_Rate', 'EGO', 'AU', 'ABX', 'BVN', 'CPI',
       'Covid_deaths', 'Interest_rate_USA', 'Interest_rate_UK',
       'Disease_volitaly_tracker', 'Gold_price_trend', 'Covid_economic_impact',
       'Stock_maket_news', 'Stock_market_crash', 'silver_price_trend',
       'Palladium_price_trend', 'Platinum_price_trend', 'Gold_ETF_Return',
       'Silver_Return', 'Platinum_Return', 'Palladium_Return'],
      dtype='object')


col_to_remove = ['Disease_volitaly_tracker']


new_df_palladium.drop(col_to_remove,axis=1,inplace=True)


scaler = MinMaxScaler()
feature_minmax_transform_data = scaler.fit_transform(new_df_palladium)
feature_minmax_transform = pd.DataFrame(columns=new_df_palladium.columns, data=feature_minmax_transform_data, index=new_df_palladium.index)
feature_minmax_transform.head()
transformed_df = feature_minmax_transform


test_size = int(0.3 * len(transformed_df))
train_size = len(transformed_df) - test_size

training_x = transformed_df[:train_size].drop('Palladium',axis=1)
training_y = transformed_df[:train_size]['Palladium']

testing_x = transformed_df[train_size:].drop(['Palladium'], axis=1)
testing_y = transformed_df[train_size:]['Palladium']


X2 = sm.add_constant(training_x)
est = sm.OLS(training_y, X2)
est2 = est.fit()
print(est2.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:              Palladium   R-squared:                       0.949
Model:                            OLS   Adj. R-squared:                  0.947
Method:                 Least Squares   F-statistic:                     365.8
Date:                Mon, 25 Jul 2022   Prob (F-statistic):          1.80e-298
Time:                        21:20:49   Log-Likelihood:                 740.50
No. Observations:                 516   AIC:                            -1429.
Df Residuals:                     490   BIC:                            -1319.
Df Model:                          25                                         
Covariance Type:            nonrobust                                         
==========================================================================================
                             coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------------------
const                      0.0944      0.077      1.220      0.223      -0.058       0.246
Gold_ETF                   0.7072      0.092      7.711      0.000       0.527       0.887
S&P_500                    0.5087      0.093      5.464      0.000       0.326       0.692
Silver                    -0.4988      0.074     -6.722      0.000      -0.645      -0.353
Platinum                   0.6341      0.056     11.395      0.000       0.525       0.743
Crude_oil                 -0.6249      0.114     -5.471      0.000      -0.849      -0.400
Euro_USD_Exchange_Rate    -0.0656      0.054     -1.215      0.225      -0.172       0.040
EGO                        0.0625      0.034      1.859      0.064      -0.004       0.129
AU                        -0.2330      0.054     -4.286      0.000      -0.340      -0.126
ABX                       -0.0596      0.056     -1.072      0.284      -0.169       0.050
BVN                        0.2007      0.038      5.251      0.000       0.126       0.276
CPI                        0.7155      0.128      5.577      0.000       0.463       0.968
Covid_deaths              -0.1249      0.027     -4.624      0.000      -0.178      -0.072
Interest_rate_USA         -0.1961      0.074     -2.649      0.008      -0.342      -0.051
Interest_rate_UK           0.0982      0.095      1.033      0.302      -0.089       0.285
Gold_price_trend          -0.0531      0.030     -1.752      0.080      -0.113       0.006
Covid_economic_impact      0.1474      0.040      3.678      0.000       0.069       0.226
Stock_maket_news           0.1363      0.018      7.655      0.000       0.101       0.171
Stock_market_crash        -0.0800      0.042     -1.901      0.058      -0.163       0.003
silver_price_trend        -0.1155      0.036     -3.200      0.001      -0.186      -0.045
Palladium_price_trend      0.6802      0.051     13.219      0.000       0.579       0.781
Platinum_price_trend      -0.2523      0.032     -7.916      0.000      -0.315      -0.190
Gold_ETF_Return           -0.0867      0.040     -2.157      0.031      -0.166      -0.008
Silver_Return              0.0704      0.052      1.345      0.179      -0.032       0.173
Platinum_Return           -0.0915      0.040     -2.262      0.024      -0.171      -0.012
Palladium_Return           0.3046      0.053      5.797      0.000       0.201       0.408
==============================================================================
Omnibus:                       10.352   Durbin-Watson:                   0.445
Prob(Omnibus):                  0.006   Jarque-Bera (JB):               10.443
Skew:                           0.319   Prob(JB):                      0.00540
Kurtosis:                       3.283   Cond. No.                         133.
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

C:\ProgramData\Anaconda3\lib\site-packages\statsmodels\tsa\tsatools.py:142: FutureWarning:

In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only


date_df = pd.DataFrame(transformed_df["Palladium"])
date_df['Date'] = date_df.index
date_df.drop(columns="Palladium",inplace=True)
date_df= date_df.squeeze()


float_data = np.array(transformed_df.values.tolist())


# Train-Test Split
nn_metal_data = float_data

split_percent = 0.70
split = int(split_percent*len(nn_metal_data))

nn_metal_train = nn_metal_data
nn_metal_test = nn_metal_data

date_train = date_df
date_test = date_df

print(len(nn_metal_train))
print(len(nn_metal_test))

737
737


look_back =3  #lags
numberOfCols = len(transformed_df.columns)
#train and test generator
train_generator = TimeseriesGenerator(nn_metal_train, nn_metal_train, length=look_back, batch_size=1)   
test_generator = TimeseriesGenerator(nn_metal_test, nn_metal_test, length=look_back, batch_size=1)


model = Sequential()
model.add(
    LSTM(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(64,
        activation='relu',
        activity_regularizer=regularizers.l2(0.01),
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.GRU(32,
        activation='relu',
        input_shape=(look_back,numberOfCols),
        return_sequences=True)
)
model.add(
    layers.LSTM(80,
        activation='relu',
        input_shape=(look_back,numberOfCols))
)

model.add(Dense(numberOfCols))
model.compile(optimizer='adam', loss='mse')

num_epochs = 25
model.fit_generator(train_generator, epochs=num_epochs, verbose=1)

C:\Users\LOCAL_~1\Temp/ipykernel_10088/1287865284.py:31: UserWarning:

`Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.

Epoch 1/25
734/734 [==============================] - 8s 5ms/step - loss: 0.0366
Epoch 2/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0175
Epoch 3/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0113
Epoch 4/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0096
Epoch 5/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0089
Epoch 6/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0082
Epoch 7/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0079
Epoch 8/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0076
Epoch 9/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0072
Epoch 10/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0069
Epoch 11/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0066
Epoch 12/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0065
Epoch 13/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0064
Epoch 14/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0059
Epoch 15/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0059
Epoch 16/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0060
Epoch 17/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0058
Epoch 18/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0055
Epoch 19/25
734/734 [==============================] - 4s 6ms/step - loss: 0.0055
Epoch 20/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0054
Epoch 21/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0054
Epoch 22/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0053
Epoch 23/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0051
Epoch 24/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0050
Epoch 25/25
734/734 [==============================] - 4s 5ms/step - loss: 0.0050

<keras.callbacks.History at 0x2165dbaf3a0>


nn_metal_train = scaler.inverse_transform(nn_metal_train)
nn_metal_test = scaler.inverse_transform(nn_metal_test)


prediction = model.predict(test_generator)
nn_metal_train = nn_metal_train.reshape((-1))
nn_metal_train = nn_metal_train[4::numberOfCols]
nn_metal_test = nn_metal_test.reshape((-1))
nn_metal_test = nn_metal_test[4::numberOfCols]
prediction = scaler.inverse_transform(prediction)
prediction = prediction.reshape((-1))
prediction = prediction[4::numberOfCols]

trace1 = go.Scatter(
    x = date_train,
    y = nn_metal_train,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = date_test,
    y = prediction,
    mode = 'lines',
    name = 'Predicted Value'
)
trace3 = go.Scatter(
    x = date_test,
    y = nn_metal_test,
    mode='lines',
    name = 'Actual values'
)
layout = go.Layout(
    title = "Price Predictions",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2, trace3], layout=layout)
fig.show()


forecast_accuracy(prediction, nn_metal_test[:734])

{'me': 3.013918543511576,
 'mae': 80.29563646862229,
 'rmse': 113.29686952957792,
 'mse': 12836.180645202203}


nn_metal_data = nn_metal_data.reshape((-1,numberOfCols))

def predict(num_prediction, model):
    
    prediction_list = nn_metal_data[-look_back:]
    for _ in range(num_prediction):
        prediction_list = prediction_list.reshape((-1,numberOfCols))
        #print(prediction_list)
        #prediction_list = scaler.inverse_transform(prediction_list)
        x = prediction_list[-look_back:]
        x = x.reshape((1,look_back, numberOfCols))
        out = model.predict(x)[0][0]
        for i in range(0,numberOfCols):
            prediction_list = np.append(prediction_list, model.predict(x)[0][i])
    prediction_list = scaler.inverse_transform(prediction_list.reshape((-1,numberOfCols)))
    prediction_list = prediction_list.reshape((-1))
    #prediction_list = prediction_list[look_back-1:]
    prediction_list = prediction_list[4::numberOfCols]
    return prediction_list
    
def predict_dates(num_prediction):
    last_date = df['Date'].values[-2]
    prediction_dates = pd.date_range(last_date, periods=num_prediction+1, freq='D').tolist()
    return prediction_dates

num_prediction = 10
forecast = predict(num_prediction, model)
forecast_dates = predict_dates(num_prediction)
forecast = forecast[1:]


nn_metal_data = scaler.inverse_transform(nn_metal_data)
nn_metal_data = nn_metal_data.reshape((-1))
nn_metal_data = nn_metal_data[4::numberOfCols]
forecast = forecast.reshape((-1))
#forecast_list1 = forecast[:5]
trace1 = go.Scatter(
    x = df['Date'],
    y = nn_metal_data,
    mode = 'lines',
    name = 'Data'
)
trace2 = go.Scatter(
    x = forecast_dates,
    y = forecast,
    mode = 'lines',
    name = 'forecast'
)

layout = go.Layout(
    title = "Forecasting Price",
    xaxis = {'title' : "Date"},
    yaxis = {'title' : "Value"}
)
fig = go.Figure(data=[trace1, trace2], layout=layout)
fig.show()

	Date	Gold_ETF	S&P_500	Silver	Platinum	Palladium	Crude_oil	Euro_USD_Exchange_Rate	EGO	AU	ABX	BVN	CPI	Interest_rate_USA	Interest_rate_UK	Disease_volitaly_tracker	Gold_price_trend	Stock_maket_news	Stock_market_crash	silver_price_trend	Palladium_price_trend	Platinum_price_trend
0	2019-06-21	1396.2	2950.46	15.273	811.5	1491.3	57.43	1.1296	5.43	16.45	19.182671	16.388355	255.361	0.74	0.38	0.00	32	0	6	8	14	56
1	2019-06-24	1414.3	2945.35	15.368	812.2	1520.4	57.90	1.1385	5.49	17.11	19.975727	16.933641	255.361	0.71	0.36	1.78	35	49	4	8	19	52
2	2019-06-25	1414.9	2917.38	15.291	810.3	1521.8	57.83	1.1400	5.45	16.65	19.667839	16.636213	255.361	0.73	0.35	0.00	35	49	4	8	19	52
3	2019-06-26	1411.6	2913.78	15.283	817.1	1518.0	59.38	1.1370	5.70	17.07	19.415928	16.477583	255.361	0.74	0.35	0.00	35	49	4	8	19	52
4	2019-06-27	1408.4	2924.92	15.205	812.6	1532.2	59.43	1.1375	5.75	17.21	19.210663	16.398270	255.361	0.71	0.36	0.55	35	49	4	8	19	52

	Gold_ETF	S&P_500	Silver	Platinum	Palladium	Crude_oil	Euro_USD_Exchange_Rate	EGO	AU	ABX	BVN	CPI	Covid_deaths	Interest_rate_USA	Interest_rate_UK	Disease_volitaly_tracker	Gold_price_trend	Covid_economic_impact	Stock_maket_news	Stock_market_crash	silver_price_trend	Palladium_price_trend	Platinum_price_trend
Date
2019-06-21	1396.2	2950.46	15.273	811.5	1491.3	57.43	1.1296	5.43	16.45	19.182671	16.388355	255.361	0	0.74	0.38	0.00	32	0	0	6	8	14	56
2019-06-24	1414.3	2945.35	15.368	812.2	1520.4	57.90	1.1385	5.49	17.11	19.975727	16.933641	255.361	0	0.71	0.36	1.78	35	0	49	4	8	19	52
2019-06-25	1414.9	2917.38	15.291	810.3	1521.8	57.83	1.1400	5.45	16.65	19.667839	16.636213	255.361	0	0.73	0.35	0.00	35	0	49	4	8	19	52
2019-06-26	1411.6	2913.78	15.283	817.1	1518.0	59.38	1.1370	5.70	17.07	19.415928	16.477583	255.361	0	0.74	0.35	0.00	35	0	49	4	8	19	52
2019-06-27	1408.4	2924.92	15.205	812.6	1532.2	59.43	1.1375	5.75	17.21	19.210663	16.398270	255.361	0	0.71	0.36	0.55	35	0	49	4	8	19	52

	Gold_ETF	S&P_500	Silver	Platinum	Palladium	Crude_oil	Euro_USD_Exchange_Rate	EGO	AU	ABX	BVN	CPI	Covid_deaths	Interest_rate_USA	Interest_rate_UK	Disease_volitaly_tracker	Gold_price_trend	Covid_economic_impact	Stock_maket_news	Stock_market_crash	silver_price_trend	Palladium_price_trend	Platinum_price_trend
Gold_ETF	1.000000	0.594901	0.808265	0.381407	0.614011	0.278021	0.377113	0.705257	0.470091	0.681161	-0.495626	0.518520	0.491924	-0.615498	0.193342	0.301835	0.290943	0.204087	-0.090103	0.001961	0.314408	0.155644	0.448615
S&P_500	0.594901	1.000000	0.720232	0.643814	0.471741	0.704071	0.305298	0.298287	-0.178688	-0.098130	-0.535643	0.785443	0.428999	-0.409345	0.234009	-0.141260	-0.167483	-0.341203	-0.149370	-0.185627	0.070664	0.102815	0.456565
Silver	0.808265	0.720232	1.000000	0.766384	0.709129	0.350812	0.686743	0.756361	0.296655	0.331152	-0.213219	0.420916	0.409257	-0.593756	-0.045910	0.006476	0.082926	-0.167328	-0.140539	-0.156577	0.346463	0.064248	0.485275
Platinum	0.381407	0.643814	0.766384	1.000000	0.672032	0.406597	0.585510	0.500324	0.024563	-0.111983	-0.067238	0.312500	0.279432	-0.302529	-0.078677	-0.184724	-0.092614	-0.397850	-0.089544	-0.142801	0.227960	0.162583	0.494881
Palladium	0.614011	0.471741	0.709129	0.672032	1.000000	0.123400	0.544304	0.583258	0.235065	0.336540	-0.249425	0.214436	0.218063	-0.499165	-0.102531	0.206928	0.178303	0.070769	0.116724	0.078800	0.214654	0.348376	0.390017
Crude_oil	0.278021	0.704071	0.350812	0.406597	0.123400	1.000000	-0.250994	-0.061457	-0.370132	-0.313191	-0.261118	0.901504	0.035913	0.265418	0.707314	-0.310902	-0.154122	-0.569342	-0.165159	-0.146092	-0.016920	0.239543	0.447860
Euro_USD_Exchange_Rate	0.377113	0.305298	0.686743	0.585510	0.544304	-0.250994	1.000000	0.646324	0.267023	0.182646	0.052024	-0.231272	0.392849	-0.702342	-0.633900	0.062029	0.025829	0.023311	-0.047962	-0.115300	0.260373	-0.168014	0.144593
EGO	0.705257	0.298287	0.756361	0.500324	0.583258	-0.061457	0.646324	1.000000	0.640633	0.609477	0.032994	0.016611	0.406305	-0.612153	-0.268603	0.162893	0.205725	0.101405	-0.107649	-0.054078	0.322836	0.023404	0.372599
AU	0.470091	-0.178688	0.296655	0.024563	0.235065	-0.370132	0.267023	0.640633	1.000000	0.835432	0.175537	-0.292529	0.098137	-0.429588	-0.250901	0.191479	0.320691	0.317865	-0.113029	-0.094936	0.256805	0.029301	0.099349
ABX	0.681161	-0.098130	0.331152	-0.111983	0.336540	-0.313191	0.182646	0.609477	0.835432	1.000000	-0.142331	-0.090895	0.203072	-0.472753	-0.035274	0.416275	0.364875	0.538219	-0.053612	0.031585	0.224481	0.036720	0.091935
BVN	-0.495626	-0.535643	-0.213219	-0.067238	-0.249425	-0.261118	0.052024	0.032994	0.175537	-0.142331	1.000000	-0.579559	-0.437015	0.367125	-0.330305	-0.434805	-0.136994	-0.384940	-0.069618	-0.238850	-0.066343	-0.108430	-0.248229
CPI	0.518520	0.785443	0.420916	0.312500	0.214436	0.901504	-0.231272	0.016611	-0.292529	-0.090895	-0.579559	1.000000	0.225116	0.056582	0.751196	-0.046183	-0.024087	-0.275264	-0.113879	-0.022940	0.032789	0.231679	0.473510
Covid_deaths	0.491924	0.428999	0.409257	0.279432	0.218063	0.035913	0.392849	0.406305	0.098137	0.203072	-0.437015	0.225116	1.000000	-0.574236	-0.116223	0.228420	0.113809	0.243240	-0.071350	0.038397	0.253668	0.030649	0.302233
Interest_rate_USA	-0.615498	-0.409345	-0.593756	-0.302529	-0.499165	0.265418	-0.702342	-0.612153	-0.429588	-0.472753	0.367125	0.056582	-0.574236	1.000000	0.564132	-0.266841	-0.169380	-0.313442	-0.003753	0.043499	-0.229509	0.002369	-0.157067
Interest_rate_UK	0.193342	0.234009	-0.045910	-0.078677	-0.102531	0.707314	-0.633900	-0.268603	-0.250901	-0.035274	-0.330305	0.751196	-0.116223	0.564132	1.000000	0.024327	0.026793	-0.111439	-0.088812	0.073137	-0.052128	0.181968	0.244112
Disease_volitaly_tracker	0.301835	-0.141260	0.006476	-0.184724	0.206928	-0.310902	0.062029	0.162893	0.191479	0.416275	-0.434805	-0.046183	0.228420	-0.266841	0.024327	1.000000	0.520181	0.734502	0.259482	0.576298	0.223547	0.191929	0.153072
Gold_price_trend	0.290943	-0.167483	0.082926	-0.092614	0.178303	-0.154122	0.025829	0.205725	0.320691	0.364875	-0.136994	-0.024087	0.113809	-0.169380	0.026793	0.520181	1.000000	0.485080	0.320490	0.574453	0.544444	0.568225	0.453146
Covid_economic_impact	0.204087	-0.341203	-0.167328	-0.397850	0.070769	-0.569342	0.023311	0.101405	0.317865	0.538219	-0.384940	-0.275264	0.243240	-0.313442	-0.111439	0.734502	0.485080	1.000000	0.144829	0.431179	0.143856	0.047053	-0.039523
Stock_maket_news	-0.090103	-0.149370	-0.140539	-0.089544	0.116724	-0.165159	-0.047962	-0.107649	-0.113029	-0.053612	-0.069618	-0.113879	-0.071350	-0.003753	-0.088812	0.259482	0.320490	0.144829	1.000000	0.491632	0.206859	0.371772	0.064993
Stock_market_crash	0.001961	-0.185627	-0.156577	-0.142801	0.078800	-0.146092	-0.115300	-0.054078	-0.094936	0.031585	-0.238850	-0.022940	0.038397	0.043499	0.073137	0.576298	0.574453	0.431179	0.491632	1.000000	0.215842	0.431137	0.165397
silver_price_trend	0.314408	0.070664	0.346463	0.227960	0.214654	-0.016920	0.260373	0.322836	0.256805	0.224481	-0.066343	0.032789	0.253668	-0.229509	-0.052128	0.223547	0.544444	0.143856	0.206859	0.215842	1.000000	0.261089	0.451579
Palladium_price_trend	0.155644	0.102815	0.064248	0.162583	0.348376	0.239543	-0.168014	0.023404	0.029301	0.036720	-0.108430	0.231679	0.030649	0.002369	0.181968	0.191929	0.568225	0.047053	0.371772	0.431137	0.261089	1.000000	0.509484
Platinum_price_trend	0.448615	0.456565	0.485275	0.494881	0.390017	0.447860	0.144593	0.372599	0.099349	0.091935	-0.248229	0.473510	0.302233	-0.157067	0.244112	0.153072	0.453146	-0.039523	0.064993	0.165397	0.451579	0.509484	1.000000

	Gold_ETF	S&P_500	Silver	Platinum	Palladium	Crude_oil	Euro_USD_Exchange_Rate	EGO	AU	ABX	BVN	CPI	Covid_deaths	Interest_rate_USA	Interest_rate_UK	Disease_volitaly_tracker	Gold_price_trend	Covid_economic_impact	Stock_maket_news	Stock_market_crash	silver_price_trend	Palladium_price_trend	Platinum_price_trend	Gold_ETF_Return	Silver_Return	Platinum_Return	Palladium_Return
Date
2019-06-21	1396.2	2950.46	15.273	811.5	1491.3	57.43	1.1296	5.43	16.45	19.182671	16.388355	255.361	0	0.74	0.38	0.00	32	0	0	6	8	14	56	NaN	NaN	NaN	NaN
2019-06-24	1414.3	2945.35	15.368	812.2	1520.4	57.90	1.1385	5.49	17.11	19.975727	16.933641	255.361	0	0.71	0.36	1.78	35	0	49	4	8	19	52	0.012964	0.006220	0.000863	0.019513
2019-06-25	1414.9	2917.38	15.291	810.3	1521.8	57.83	1.1400	5.45	16.65	19.667839	16.636213	255.361	0	0.73	0.35	0.00	35	0	49	4	8	19	52	0.000424	-0.005010	-0.002339	0.000921
2019-06-26	1411.6	2913.78	15.283	817.1	1518.0	59.38	1.1370	5.70	17.07	19.415928	16.477583	255.361	0	0.74	0.35	0.00	35	0	49	4	8	19	52	-0.002332	-0.000523	0.008392	-0.002497
2019-06-27	1408.4	2924.92	15.205	812.6	1532.2	59.43	1.1375	5.75	17.21	19.210663	16.398270	255.361	0	0.71	0.36	0.55	35	0	49	4	8	19	52	-0.002267	-0.005104	-0.005507	0.009354

	Gold_ETF	S&P_500	Silver	Platinum	Palladium	Crude_oil	Euro_USD_Exchange_Rate	EGO	AU	ABX	BVN	CPI	Covid_deaths	Interest_rate_USA	Disease_volitaly_tracker	Gold_price_trend	Stock_maket_news	Stock_market_crash	silver_price_trend	Palladium_price_trend	Platinum_price_trend	Gold_ETF_Return
Date
2019-06-24	0.026878	0.276961	0.205684	0.311357	0.076525	0.592140	0.583079	0.036957	0.150886	0.046521	0.943730	0.0	0.059689	0.733696	0.026035	0.155844	0.49	0.0	0.010753	0.10989	0.213115	0.574306
2019-06-25	0.027795	0.266018	0.201325	0.308622	0.077408	0.591706	0.589621	0.032609	0.130999	0.030190	0.918152	0.0	0.059689	0.744565	0.000000	0.155844	0.49	0.0	0.010753	0.10989	0.213115	0.459543
2019-06-26	0.022755	0.264610	0.200872	0.318411	0.075013	0.601314	0.576537	0.059783	0.149157	0.016827	0.904511	0.0	0.059689	0.750000	0.000000	0.155844	0.49	0.0	0.010753	0.10989	0.213115	0.434314
2019-06-27	0.017868	0.268968	0.196456	0.311933	0.083964	0.601624	0.578718	0.065217	0.155210	0.005939	0.897690	0.0	0.059689	0.733696	0.008044	0.155844	0.49	0.0	0.010753	0.10989	0.213115	0.434913
2019-06-28	0.019853	0.275556	0.199173	0.344897	0.084090	0.595673	0.577846	0.072826	0.153048	0.009898	0.908774	0.0	0.059689	0.739130	0.000000	0.155844	0.49	0.0	0.010753	0.10989	0.213115	0.464108

Data Preprocessing¶

Gold¶

Silver¶

Palladium¶

Platinum¶

Building Models¶

Gold¶

Neural network - Gold¶

Forecasting - Gold¶

Silver¶

Neural network-Silver¶

Forecasting - Silver¶

Platinum¶

Neural network-Platinum¶

Forecasting - Platinum¶

Palladium¶

Neural network-Palladium¶

Forecasting - Palladium¶